Update app.py

app.py

@@ -4,10 +4,20 @@ import modin.pandas as pd
 from diffusers import DiffusionPipeline 
 
 device = "cuda" if torch.cuda.is_available() else "cpu"
-
+if torch.cuda.is_available():
+    PYTORCH_CUDA_ALLOC_CONF={'max_split_size_mb': 6000}
+    torch.cuda.max_memory_allocated(device=device)
+    torch.cuda.empty_cache()
+    pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", torch_dtype=torch.float16, variant="fp16", use_safetensors=True)
+    pipe.enable_xformers_memory_efficient_attention()
+    pipe = pipe.to(device)
+    torch.cuda.empty_cache()
+    refiner = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-refiner-1.0", use_safetensors=True, torch_dtype=torch.float16, variant="fp16")
+    refiner.enable_xformers_memory_efficient_attention()
+    refiner.enable_sequential_cpu_offload()
+else: 
 pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", use_safetensors=True)
 pipe = pipe.to(device)
-
 refiner = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-refiner-1.0", use_safetensors=True)
 refiner = refiner.to(device)